Add ap_cstr_casecmp[n]() - placeholder of apr_cstr_casecmp[n] functions

for case-insensitive C/POSIX-locale token comparison.

Submitted by: wrowe
Reviewed by: jim, minfrin

git-svn-id: https://svn.apache.org/repos/asf/httpd/httpd/branches/2.4.x@1748334 13f79535-47bb-0310-9956-ffa450edef68

diff --git a/CHANGES b/CHANGES
index e6840fb008a8436f3a3801f40f822ff8a21cbc04..b032de44de73078b73b79162d1df07864c6c521c 100644 (file)
--- a/CHANGES
+++ b/CHANGES
@@ -2,6 +2,10 @@
 
 Changes with Apache 2.4.21
 
+  *) Add ap_cstr_casecmp[n]() - placeholder of apr_cstr_casecmp[n] functions
+     for case-insensitive C/POSIX-locale token comparison.
+     [Jim Jagielski, William Rowe, Yann Ylavic, Branko Čibej]
+
   *) mod_userdir: Constify and save a few bytes in the conf pool when
      parsing the "UserDir" directive. [Christophe Jaillet]
 

diff --git a/STATUS b/STATUS
index 996abb0e94041febb14380bb0007af63f415d71b..c9e90e52e921bd423e011862709c0fd7a682df4e 100644 (file)
--- a/STATUS
+++ b/STATUS
@@ -114,28 +114,6 @@ RELEASE SHOWSTOPPERS:
 PATCHES ACCEPTED TO BACKPORT FROM TRUNK:
   [ start all new proposals below, under PATCHES PROPOSED. ]
 
-  *) util: Backport apr_cstr_casecmp[n] - without consideration of APR's
-     release for the time being...
-     trunk patches: http://svn.apache.org/r1715401
-                    http://svn.apache.org/r1715404
-                    http://svn.apache.org/r1715524
-                    http://svn.apache.org/r1715526
-                    http://svn.apache.org/r1715527
-                    http://svn.apache.org/r1715546
-                    http://svn.apache.org/r1715632
-                    http://svn.apache.org/r1715736
-                    http://svn.apache.org/r1715859
-                    http://svn.apache.org/r1722194
-                    http://svn.apache.org/r1747468
-                    http://svn.apache.org/r1747478
-                    http://svn.apache.org/r1747483
-                    http://svn.apache.org/r1747484
-     2.4.x rollup patch: Above applies, modulo ap_mmn.h/CHANGES, captured here;
-         http://raw.githubusercontent.com/wrowe/patches/master/backport-2.4-ap_cstr_casecmp-fns.patch
-         [corrected SVN credits to brane, who added the thing]
-     +1: wrowe, jim, minfrin
-
-
 
 PATCHES PROPOSED TO BACKPORT FROM TRUNK:
   [ New proposals should be added at the end of the list ]

diff --git a/include/ap_mmn.h b/include/ap_mmn.h
index 73f3c656e6f1b2718f4476611c88a2159aec5fa0..54cbbee4783165668b892c167d10e3266a646544 100644 (file)
--- a/include/ap_mmn.h
+++ b/include/ap_mmn.h
@@ -476,6 +476,7 @@
  *                          ap_proxy_is_socket_connected() and
  *                          extended proxy_worker_shared.
  * 20120211.60 (2.4.21-dev) Add dav_get_provider_name.
+ * 20120211.61 (2.4.21-dev) Add ap_cstr_casecmp[n]() - placeholder of apr_ fns
  */
 
 #define MODULE_MAGIC_COOKIE 0x41503234UL /* "AP24" */
@@ -483,7 +484,7 @@
 #ifndef MODULE_MAGIC_NUMBER_MAJOR
 #define MODULE_MAGIC_NUMBER_MAJOR 20120211
 #endif
-#define MODULE_MAGIC_NUMBER_MINOR 60                   /* 0...n */
+#define MODULE_MAGIC_NUMBER_MINOR 61                   /* 0...n */
 
 /**
  * Determine if the server's current MODULE_MAGIC_NUMBER is at least a

diff --git a/include/httpd.h b/include/httpd.h
index 72b83945278bea54b158c9c810c588cd8e9cdffe..5035a6100a565d5eb2abe8c3f09c2d8e262ae656 100644 (file)
--- a/include/httpd.h
+++ b/include/httpd.h
@@ -2341,6 +2341,34 @@ AP_DECLARE(int) ap_array_str_index(const apr_array_header_t *array,
 AP_DECLARE(int) ap_array_str_contains(const apr_array_header_t *array, 
                                       const char *s);
 
+/**
+ * Perform a case-insensitive comparison of two strings @a atr1 and @a atr2,
+ * treating upper and lower case values of the 26 standard C/POSIX alphabetic
+ * characters as equivalent. Extended latin characters outside of this set
+ * are treated as unique octets, irrespective of the current locale.
+ *
+ * Returns in integer greater than, equal to, or less than 0,
+ * according to whether @a str1 is considered greater than, equal to,
+ * or less than @a str2.
+ *
+ * @note Same code as apr_cstr_casecmp, which arrives in APR 1.6
+ */
+AP_DECLARE(int) ap_cstr_casecmp(const char *s1, const char *s2);
+
+/**
+ * Perform a case-insensitive comparison of two strings @a atr1 and @a atr2,
+ * treating upper and lower case values of the 26 standard C/POSIX alphabetic
+ * characters as equivalent. Extended latin characters outside of this set
+ * are treated as unique octets, irrespective of the current locale.
+ *
+ * Returns in integer greater than, equal to, or less than 0,
+ * according to whether @a str1 is considered greater than, equal to,
+ * or less than @a str2.
+ *
+ * @note Same code as apr_cstr_casecmpn, which arrives in APR 1.6
+ */
+AP_DECLARE(int) ap_cstr_casecmpn(const char *s1, const char *s2, apr_size_t n);
+
 #ifdef __cplusplus
 }
 #endif

diff --git a/server/util.c b/server/util.c
index 674118e8ed61d60d2e58584b2e338d7192ef4b85..06da789718bd8a9ea196dc5539164d8dcfa4fa54 100644 (file)
--- a/server/util.c
+++ b/server/util.c
@@ -96,7 +96,6 @@
 #undef APLOG_MODULE_INDEX
 #define APLOG_MODULE_INDEX AP_CORE_MODULE_INDEX
 
-
 /*
  * Examine a field value (such as a media-/content-type) string and return
  * it sans any parameters; e.g., strip off any ';charset=foo' and the like.
@@ -3173,3 +3172,128 @@ AP_DECLARE(int) ap_array_str_contains(const apr_array_header_t *array,
     return (ap_array_str_index(array, s, 0) >= 0);
 }
 
+#if !APR_CHARSET_EBCDIC
+/*
+ * Our own known-fast translation table for casecmp by character.
+ * Only ASCII alpha characters 41-5A are folded to 61-7A, other
+ * octets (such as extended latin alphabetics) are never case-folded.
+ * NOTE: Other than Alpha A-Z/a-z, each code point is unique!
+ */
+static const short ucharmap[] = {
+    0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7,
+    0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe,  0xf,
+    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
+    0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
+    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
+    0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
+    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+    0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
+    0x40,  'a',  'b',  'c',  'd',  'e',  'f',  'g',
+     'h',  'i',  'j',  'k',  'l',  'm',  'n',  'o',
+     'p',  'q',  'r',  's',  't',  'u',  'v',  'w',
+     'x',  'y',  'z', 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
+    0x60,  'a',  'b',  'c',  'd',  'e',  'f',  'g',
+     'h',  'i',  'j',  'k',  'l',  'm',  'n',  'o',
+     'p',  'q',  'r',  's',  't',  'u',  'v',  'w',
+     'x',  'y',  'z', 0x7b, 0x7c, 0x7d, 0x7e, 0x7f,
+    0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
+    0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
+    0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97,
+    0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
+    0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
+    0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
+    0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7,
+    0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
+    0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7,
+    0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
+    0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7,
+    0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
+    0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7,
+    0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
+    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7,
+    0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff
+};
+#else /* APR_CHARSET_EBCDIC */
+/*
+ * Derived from apr-iconv/ccs/cp037.c for EBCDIC case comparison,
+ * provides unique identity of every char value (strict ISO-646
+ * conformance, arbitrary election of an ISO-8859-1 ordering, and
+ * very arbitrary control code assignments into C1 to achieve
+ * identity and a reversible mapping of code points),
+ * then folding the equivalences of ASCII 41-5A into 61-7A, 
+ * presenting comparison results in a somewhat ISO/IEC 10646
+ * (ASCII-like) order, depending on the EBCDIC code page in use.
+ *
+ * NOTE: Other than Alpha A-Z/a-z, each code point is unique!
+ */
+static const short ucharmap[] = {
+    0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F,
+    0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+    0x10, 0x11, 0x12, 0x13, 0x9D, 0x85, 0x08, 0x87,
+    0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
+    0x80, 0x81, 0x82, 0x83, 0x84, 0x0A, 0x17, 0x1B,
+    0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
+    0x90, 0x91, 0x16, 0x93, 0x94, 0x95, 0x96, 0x04,
+    0x98, 0x99, 0x9A, 0x9B, 0x14, 0x15, 0x9E, 0x1A,
+    0x20, 0xA0, 0xE2, 0xE4, 0xE0, 0xE1, 0xE3, 0xE5,
+    0xE7, 0xF1, 0xA2, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
+    0x26, 0xE9, 0xEA, 0xEB, 0xE8, 0xED, 0xEE, 0xEF,
+    0xEC, 0xDF, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0xAC,
+    0x2D, 0x2F, 0xC2, 0xC4, 0xC0, 0xC1, 0xC3, 0xC5,
+    0xC7, 0xD1, 0xA6, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
+    0xF8, 0xC9, 0xCA, 0xCB, 0xC8, 0xCD, 0xCE, 0xCF,
+    0xCC, 0x60, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
+    0xD8, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+    0x68, 0x69, 0xAB, 0xBB, 0xF0, 0xFD, 0xFE, 0xB1,
+    0xB0, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70,
+    0x71, 0x72, 0xAA, 0xBA, 0xE6, 0xB8, 0xC6, 0xA4,
+    0xB5, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78,
+    0x79, 0x7A, 0xA1, 0xBF, 0xD0, 0xDD, 0xDE, 0xAE,
+    0x5E, 0xA3, 0xA5, 0xB7, 0xA9, 0xA7, 0xB6, 0xBC,
+    0xBD, 0xBE, 0x5B, 0x5D, 0xAF, 0xA8, 0xB4, 0xD7,
+    0x7B, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
+    0x68, 0x69, 0xAD, 0xF4, 0xF6, 0xF2, 0xF3, 0xF5,
+    0x7D, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70,
+    0x71, 0x72, 0xB9, 0xFB, 0xFC, 0xF9, 0xFA, 0xFF,
+    0x5C, 0xF7, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78,
+    0x79, 0x7A, 0xB2, 0xD4, 0xD6, 0xD2, 0xD3, 0xD5,
+    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
+    0x38, 0x39, 0xB3, 0xDB, 0xDC, 0xD9, 0xDA, 0x9F
+};
+#endif
+
+AP_DECLARE(int) ap_cstr_casecmp(const char *s1, const char *s2)
+{
+    const unsigned char *str1 = (const unsigned char *)s1;
+    const unsigned char *str2 = (const unsigned char *)s2;
+    for (;;)
+    {
+        const int c1 = (int)(*str1);
+        const int c2 = (int)(*str2);
+        const int cmp = ucharmap[c1] - ucharmap[c2];
+        /* Not necessary to test for !c2, this is caught by cmp */
+        if (cmp || !c1)
+            return cmp;
+        str1++;
+        str2++;
+    }
+}
+
+AP_DECLARE(int) ap_cstr_casecmpn(const char *s1, const char *s2, apr_size_t n)
+{
+    const unsigned char *str1 = (const unsigned char *)s1;
+    const unsigned char *str2 = (const unsigned char *)s2;
+    while (n--)
+    {
+        const int c1 = (int)(*str1);
+        const int c2 = (int)(*str2);
+        const int cmp = ucharmap[c1] - ucharmap[c2];
+        /* Not necessary to test for !c2, this is caught by cmp */
+        if (cmp || !c1)
+            return cmp;
+        str1++;
+        str2++;
+    }
+    return 0;
+}
+